Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3604 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1047475 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.6497. Min Act: -0.0000

Data Index: 180493 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.6342. Min Act: -0.0000

Data Index: 536831 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5658. Min Act: -0.0000

Data Index: 200690 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.6067. Min Act: -0.0000

Data Index: 985639 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5772. Min Act: -0.0000

Data Index: 501223 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5898. Min Act: -0.0000

Data Index: 816911 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5309. Min Act: -0.0000

Data Index: 39414 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5105. Min Act: -0.0000

Data Index: 822615 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5159. Min Act: -0.0000

Data Index: 836673 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5306. Min Act: -0.0000

Data Index: 390729 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4735. Min Act: -0.0000

Data Index: 362267 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4968. Min Act: -0.0000

Data Index: 820461 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4917. Min Act: -0.0000

Data Index: 422809 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4913. Min Act: -0.0000

Data Index: 774862 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1079487 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.5000. Min Act: -0.0000

Data Index: 463160 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4714. Min Act: -0.0000

Data Index: 313249 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4587. Min Act: -0.0000

Data Index: 966640 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.7004. Min Range: -0.7004

Max Act: 0.4596. Min Act: -0.0000

Data Index: 886054 (C4 (Web Text))

Max Activating Token Index: 446